© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116541
    Prev
    Next
    INDEX
    Explanations

    score or rank

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zhi
    -0.06
     isEmpty
    -0.06
     the
    -0.06
    俳
    -0.06
     Radical
    -0.05
     βρίσκεται
    -0.05
     Freiheit
    -0.05
     sometimes
    -0.05
     infrequently
    -0.05
    conoc
    -0.05
    POSITIVE LOGITS
     provavelmente
    0.08
     stopni
    0.07
     Soldiers
    0.07
     malheureusement
    0.06
     свое
    0.06
     originally
    0.06
     destined
    0.06
     submersible
    0.06
     designed
    0.06
    Originally
    0.06
    Activations Density 0.008%

    No Known Activations